LLM/Large Language Model The
large language model learns patterns in language through large-scale training and is used for tasks such as generating, understanding, and transforming text.
Read article ↗TOKEN WIKI / Industry Knowledge Base
Understanding word elements starts with a concept.
has 52 introductory entries, starting from word units, computing power going overseas, and word units going overseas, covering models, reasoning, API billing and global delivery.
All termsword elements and billingcomputing power basismodel and inferenceinference performanceoverseas and architectureSearch and DiscoveryAI development toolsintelligent body and application
8 个词条
Inference / Inference
Inference is the process of using a trained model to calculate new inputs and generate outputs, which is different from training, which updates model parameters.
Read article ↗Reasoning Model / Reasoning Model The
inference model focuses on step-by-step processing and inference of complex problems, and is commonly used in mathematics, coding and multi-constraint tasks.
Read article ↗multi-modal model The
multi-modal model can handle multiple forms of information such as text, images, audio or video, and the specific support range varies by model.
Read article ↗context window
The context window is the range of Tokens that the model can accommodate at one time, usually involving input and output budgets.
Read article ↗Prompt / prompt word
Prompt words are input content used to describe tasks, context, output requirements and constraints.
Read article ↗Distillation / Knowledge Distillation
model distillation is to use the output, probability distribution or intermediate information of the teacher model to train the student model so that it can learn part of the teacher's capabilities on the target task.
Read article ↗Muse Spark / Meta model series
Muse Spark is Meta's model series, which provides reasoning and multi-modal capabilities for Meta AI, Muse and other products and related developer portals. The specific capabilities depend on the model.
Read article ↗